Learning Dense Features for Point Cloud Registration Using Graph Attention Network

by   Lai Dang Quoc Vinh, et al.

Point cloud registration is a fundamental task in many applications such as localization, mapping, tracking, and reconstruction. The successful registration relies on extracting robust and discriminative geometric features. Existing learning-based methods require high computing capacity for processing a large number of raw points at the same time. Although these approaches achieve convincing results, they are difficult to apply in real-world situations due to high computational costs. In this paper, we introduce a framework that efficiently and economically extracts dense features using graph attention network for point cloud matching and registration (DFGAT). The detector of the DFGAT is responsible for finding highly reliable key points in large raw data sets. The descriptor of the DFGAT takes these key points combined with their neighbors to extract invariant density features in preparation for the matching. The graph attention network uses the attention mechanism that enriches the relationships between point clouds. Finally, we consider this as an optimal transport problem and use the Sinkhorn algorithm to find positive and negative matches. We perform thorough tests on the KITTI dataset and evaluate the effectiveness of this approach. The results show that this method with the efficiently compact keypoint selection and description can achieve the best performance matching metrics and reach highest success ratio of 99.88


page 1

page 2

page 3

page 4


End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

3D Point cloud registration is still a very challenging topic due to the...

Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registration

The current point cloud registration methods are mainly based on geometr...

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

A successful point cloud registration often lies on robust establishment...

DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration

We present DeepICP - a novel end-to-end learning-based 3D point cloud re...

Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration

3D Point clouds are a rich source of information that enjoy growing popu...

Attention-based Vehicle Self-Localization with HD Feature Maps

We present a vehicle self-localization method using point-based deep neu...

SGFeat: Salient Geometric Feature for Point Cloud Registration

Point Cloud Registration (PCR) is a critical and challenging task in com...

Please sign up or login with your details

Forgot password? Click here to reset